AIbase
Product LibraryTool Navigation

qlearning

Public

This project focuses on implementing value iteration and Q-learning algorithms. We first test these agents in a Gridworld environment, then apply them to control a simulated robot (Crawler) and to the Pacman game. (Source: Berkeley's public projects and labs)

Creat2023-04-15T11:16:12
Update2024-09-11T09:16:42
0
Stars
0
Stars Increase

Related projects